An evidential classifier based on Dempster-Shafer theory and deep learning

Zheng Tong (1) , Philippe Xu (1) , Thierry Denoeux (1, 2)

1 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes [Compiègne]
2 IUF - Institut universitaire de France

We propose a new classifier based on Dempster-Shafer (DS) theory and a convolutional neural network (CNN) architecture for set-valued classification. In this classifier, called the evidential deep-learning classifier, convolutional and pooling layers first extract highdimensional features from input data. The features are then converted into mass functions and aggregated by Dempster's rule in a DS layer. Finally, an expected utility layer performs set-valued classification based on mass functions. We propose an end-to-end learning strategy for jointly updating the network parameters. Additionally, an approach for selecting partial multi-class acts is proposed. Experiments on image recognition, signal processing, and semantic-relationship classification tasks demonstrate that the proposed combination of deep CNN, DS layer, and expected utility layer makes it possible to improve classification accuracy and to make cautious decisions by assigning confusing patterns to multi-class sets.

Mots clés: Evidence theory; belief function; convolutional neural network; decision analysis; classification

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]

Zheng Tong, Philippe Xu, Thierry Denoeux. An evidential classifier based on Dempster-Shafer theory and deep learning. Neurocomputing, 2021, 450, pp.275-293. ⟨10.1016/j.neucom.2021.03.066⟩. ⟨hal-03219203⟩